{
  "id": 17043760,
  "title": "Run Maya 2 Native locally: streaming TTS in 12 languages",
  "url": "https://urgent.news/2026/10/29/run-maya-2-native-locally-streaming-tts-in-12-languages",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-10-29T10:12:10.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/dheemanth_reddy_15562089c/run-maya-2-native-locally-streaming-tts-in-12-languages-33f6"
  },
  "original_language": "en",
  "account": "Maya Research has launched Maya 2 Native, a text-to-speech model supporting 11 Indic languages and English. The open-source weights and inference code are available under Apache-2.0, with 20 voices, streaming audio, and voice cloning from short reference recordings. Key features include 24 kHz mono audio, streaming capabilities, and support for voice cloning with 3-10 seconds of input. The model can be installed using Python 3.10-3.12 and an NVIDIA GPU with CUDA 12.8. A Python API, OpenAI-compatible endpoint, and WebSocket streaming are provided, with steady-state latency of 111-242 ms and throughput of 323 seconds of audio per second on a H100 NVL 224. Evaluation shows 3.49% Character Error Rate across six thousand held-out texts, with good voice identity retention. Assamese remains a challenging language. Feedback from developers is welcomed to prioritize improvements in future releases.",
  "summary": "We’re releasing Maya 2 Native , a text-to-speech model from Maya Research for 11 Indic languages and English . The weights and inference code are available under Apache-2.0 , with 20 built-in voices , streaming audio, and voice cloning from 3–10 seconds of reference speech . Get the weights · Inference code · Full model card and evaluations Watch the launch video Hear it first The model supports…",
  "key_points": [
    "Maya 2 Native supports 11 Indic languages and English",
    "Open-source weights and inference code available under Apache-2.0 license",
    "Streaming TTS in 24 kHz mono audio with voice cloning capability"
  ],
  "editors_take": "Releasing open-source weights and an OpenAI-compatible endpoint lowers the barrier for developers to integrate high-speed, multilingual voice cloning and streaming into their own local applications.",
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}